Hugging Face's logo

tchbcb
/
qwenjev

Model card Files
xet
 Community
qwenjev / ops

Commit History

  1. QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified)

    tchbcb
    Verified signature
    ee7b84a

  2. QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified)

    tchbcb
    Verified signature
    4946ec2

  3. QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified)

    tchbcb
    Verified signature
    c114012

  4. Upload ops/random_baseline_runfile.py with huggingface_hub

    tchbcb
    Verified signature
    410d9e8

  5. Upload ops/v5_daemon.py with huggingface_hub

    tchbcb
    Verified signature
    9132252

  6. Upload ops/teach_server.py with huggingface_hub

    tchbcb
    Verified signature
    1169888

  7. Upload ops/random_baseline_runfile.py with huggingface_hub

    tchbcb
    Verified signature
    831ed01

  8. v0.4.10 fix2: REAL25_YAML env-aware (out_dir/dataset_dir) — hardcode trained v4b into v4 dir on old data; QWENJEV_DATASET env added

    tchbcb
    Verified signature
    7c3e866

  1. v0.4.10: heads-WIP upload hole (FUKJA61G lesson) + recover fixes (archive root, shutil.move nest, stamps prep/data only, max_steps 110)

    tchbcb
    Verified signature
    aac43ff

  2. v0.4.9: vision-aware pooling (RCA fix) + v4 namespace + eps0.45 collect config

    tchbcb
    Verified signature
    254b24b

  3. v0.4.9: vision-aware pooling (RCA fix) + v4 namespace + eps0.45 collect config

    tchbcb
    Verified signature
    6b5e2b0

  4. v0.4.8: safetensors-loss fix + HEAD verification + v0.4.7 OOM-gate sync

    tchbcb
    Verified signature
    ae3408c

  5. v0.4.8: safetensors-loss fix + HEAD verification + v0.4.7 OOM-gate sync

    tchbcb
    Verified signature
    8ecf30c

  6. QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified)

    tchbcb
    Verified signature
    d58a3db

  7. v3: real-games training round tooling

    tchbcb
    Verified signature
    59a4999

  8. v3: real-games training round tooling

    tchbcb
    Verified signature
    ef24e1d

  9. QwenJev v0.4.3: 25-public-games eval in-repo (run_eval incremental report, fetch_games, CPU feasibility verified)

    tchbcb
    Verified signature
    2bc1c6b

  1. ops/run_eval: fix local_dir must be repo-level dir (sub-path doubling bug, caught in live test)

    tchbcb
    Verified signature
    f9d9abd

  2. ops/run_eval: fix hf: path resolution (keep sub-path slashes — files land where hf_hub_download puts them)

    tchbcb
    Verified signature
    b47dcca

  3. ops/run_eval: clearer arc-agi setup hint in preflight error

    tchbcb
    Verified signature
    ff82abf

  4. ops/README: run_eval.py entry (v0.4.1)

    tchbcb
    Verified signature
    3fb97d8

  5. ops: one-command eval entry (checkpoint resolve + adapter reassembly + auto backend + provenance report)

    tchbcb
    Verified signature
    d272b05

  6. ops/: add executor + adapter sharder + note pusher (sync complete)

    tchbcb
    Verified signature
    497855c

  7. ops/kaggle_kernel: ready-to-push submission bundle

    tchbcb
    Verified signature
    2431cb4

  8. ops/: T4 pipeline toolbox (pipeline/scale/executor/sharder/smoke/NVRTC tar/README)

    tchbcb
    Verified signature
    997a2c4